Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation

TL;DR

This paper introduces a novel domain feature decoupling method using adapters for cross-domain few-shot segmentation, effectively addressing domain gap and data scarcity challenges.

Contribution

It reveals that adapters naturally serve as domain decouplers and proposes the DFN structure-based decoupler to improve cross-domain segmentation performance.

Findings

Outperforms state-of-the-art by 2.69% and 4.68% MIoU in 1-shot and 5-shot scenarios.

Demonstrates the effectiveness of structure-based domain decoupling.

Validates the approach across multiple cross-domain segmentation tasks.

Abstract

Cross-domain few-shot segmentation (CD-FSS) is proposed to pre-train the model on a source-domain dataset with sufficient samples, and then transfer the model to target-domain datasets where only a few samples are available for efficient fine-tuning. There are majorly two challenges in this task: (1) the domain gap and (2) fine-tuning with scarce data. To solve these challenges, we revisit the adapter-based methods, and discover an intriguing insight not explored in previous works: the adapter not only helps the fine-tuning of downstream tasks but also naturally serves as a domain information decoupler. Then, we delve into this finding for an interpretation, and find the model's inherent structure could lead to a natural decoupling of domain information. Building upon this insight, we propose the Domain Feature Navigator (DFN), which is a structure-based decoupler instead of loss-based ones like current works, to capture domain-specific information, thereby directing the model's attention towards domain-agnostic knowledge. Moreover, to prevent the potential excessive overfitting of DFN during the source-domain training, we further design the SAM-SVN method to constrain DFN from learning sample-specific knowledge. On target domains, we freeze the model and fine-tune the DFN to learn target-specific knowledge specific. Extensive experiments demonstrate that our method surpasses the state-of-the-art method in CD-FSS significantly by 2.69% and 4.68% MIoU in 1-shot and 5-shot scenarios, respectively.